BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 1
DTSTART;TZID=America/Denver:20240801T104500
DTEND;TZID=America/Denver:20240801T121500
UID:siggraph_SIGGRAPH 2024_sess147@linklings.com
SUMMARY:Video Generation
DESCRIPTION:X-Portrait: Expressive Portrait Animation With Hierarchical Mo
 tion Attention\n\nWe propose X-Portrait, an innovative conditional diffusi
 on model tailored for generating expressive and temporally coherent portra
 it animation. Specifically, given a single portrait as appearance referenc
 e, we aim to animate it with motion derived from a driving video, capturin
 g both highly dynamic ...\n\n\nYou Xie, Hongyi Xu, Guoxian Song, Chao Wang
 , Yichun Shi, and Linjie Luo (ByteDance Inc.)\n---------------------\nVide
 o Generation - Interactive Discussion\n\nAfter the summary presentations, 
 attendees will participate in an interactive discussion. Distributed aroun
 d the room will be a series of poster boards for authors to gather around 
 with the audience. Authors are invited to bring any material related to th
 eir paper that could instigate further conver...\n\n---------------------\
 nDirect-a-Video: Customized Video Generation With User-directed Camera Mov
 ement and Object Motion\n\nWe introduce Direct-a-Video, a text-to-video ge
 neration tool that goes beyond simple text instructions by allowing indivi
 dual or joint control over camera movements and object motion. It simplifi
 es customized video creation, enabling users to craft videos with their pr
 eferred motion patterns, as if ...\n\n\nShiyuan Yang (Tianjin University, 
 City University of Hong Kong); Liang Hou, Haibin Huang, Chongyang Ma, Peng
 fei Wan, and DI Zhang (Kuaishou Technology); Xiaodong Chen (Tianjin Univer
 sity); and Jing Liao (City University of Hong Kong)\n---------------------
 \nMotionCtrl: A Unified and Flexible Motion Controller for Video Generatio
 n\n\nMotionCtrl, through the delicate design of architecture, training str
 ategy, and curated datasets, enables independent or combined control of ca
 mera and object motion within a unified video generation model. Its genera
 lizability extends to existing video generation models like LVDM/VideoCraf
 ter1 and ...\n\n\nZhouxia Wang (University of Hong Kong); Ziyang Yuan (Tsi
 nghua University); Xintao Wang (ARC Lab, Tencent PCG); Yaowei Li (Peking U
 niversity); Tianshui Chen (Guangdong University of Technology); Menghan Xi
 a (Tencent AI Lab); Ping Luo (University of Hong Kong); and Ying Shan (ARC
  Lab, Tencent PCG)\n---------------------\nMotion-I2V: Consistent and Cont
 rollable Image-to-video Generation With Explicit Motion Modeling\n\nPlease
  see our anonymous project page for more results: \url{https://anonymous-2
 718281.github.io}.\n\n\nXiaoyu Shi, Zhaoyang Huang, Fu-Yun Wang, Weikang B
 ian, and Dasong Li (The Chinese University of Hong Kong); Yi Zhang (SenseT
 ime); Manyuan Zhang (The Chinese University of Hong Kong); Ka Chun Cheung 
 and Simon See (NVIDIA); Hongwei Qin (SenseTime); Jifeng Dai (Tsinghua Univ
 ersity); and Hongsheng Li (The Chinese University of Hong Kong)\n---------
 ------------\nPromptable Game Models: Text-Guided Game Simulation via Mask
 ed Diffusion Models\n\nWe propose Promptable Game Models (PGMs), models of
  games that can be controlled through natural language actions and desired
  game states. States are modeled through a masked diffusion transformer an
 d rendered through a compositional NeRF. Our PGM outperforms existing neur
 al video game simulators, u...\n\n\nWilli Menapace and Aliaksandr Siarohin
  (Snap); Stéphane Lathuilière (Paris Telecom LTCI, Institut Polytechnique 
 de Paris); Panos Achlioptas (Snap); Vladislav Golyanik (Max Planck Institu
 te for Informatics); Sergey Tulyakov (Snap); Elisa Ricci (Universita degli
  Studi di Trento Fondazione Bruno Kessler); and Willi Menapace\n----------
 -----------\nI2V-Adapter: A General Image-to-Video Adapter for Diffusion M
 odels\n\nWe propose I2V-Adapter, a lightweight adapter module for Image-to
 -Video generation. Our method achieves excellent performance in general I2
 V scenarios and is also compatible with various plugins from the Stable Di
 ffusion open-source community. Additionally, we propose Frame-Similarity-P
 rior to contr...\n\n\nXun Guo (University of Science and Technology of Chi
 na); Mingwu Zheng, Liang Hou, Yuan Gao, Yufan Deng, Pengfei Wan, and Di Zh
 ang (Kuaishou Technology); Yufan Liu and Weiming Hu (Institute of Automati
 on, Chinese Academy of Sciences); Zhengjun Zha (University of Science and 
 Technology of China); and Haibin Huang and Chongyang Ma (Kuaishou Technolo
 gy)\n\nInterest Area: Research & Education\n\nRegistration Category: Full 
 Conference, Full Conference Supporter, Virtual Access, Exhibitor Full Conf
 erence, Thursday\n\nSession Chair: Lin Gao (University of Chinese Academy 
 of Sciences)
END:VEVENT
END:VCALENDAR